Method and apparatus in a node for wireless communication

Abstract

The application provides a method and device in a node for wireless communication, and relates to the technical field of communication. The method comprises the following steps: a first node determines first information corresponding to first channel measurement information based on a first mapping relationship, wherein the first information is used for downlink channel precoding; the first node acquires reference information corresponding to second channel measurement information; and the first node sends second information based on the first information and / or the reference information, wherein the second information is used for determining whether to replace the first mapping relationship or determining whether the first mapping relationship is working properly. The first mapping relationship comprises a first codebook or a first artificial intelligence model. The scheme helps to realize the suitability evaluation and timely replacement of the mapping relationship, and guarantees the accuracy of the downlink channel precoding.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to methods and apparatus in nodes for wireless communication. Background Technology

[0002] In existing wireless communication systems, due to the complexity of the wireless environment and the variety of device operating environments, how to determine whether the mapping relationship (such as codebook or artificial intelligence model) used to perform dimensionality reduction transformation of channel measurement information is still applicable is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0003] This application provides methods and apparatus for use in nodes for wireless communication. The various aspects covered by this application are described below.

[0004] In a first aspect, a method for a first node in wireless communication is provided. The method includes: determining first information corresponding to first channel measurement information based on a first mapping relationship, wherein the first information is used for downlink channel precoding; obtaining reference information corresponding to second channel measurement information; and transmitting second information based on the first information and / or the reference information, wherein the second information is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0005] It's understandable that both codebooks and AI / machine learning-based channel state information (CSO) compression models are essentially mapping relationships: the first node determines the information used for downlink channel precoding based on the CSO information through this mapping relationship. In codebook-based scenarios, this mapping relationship manifests as selecting the optimal precoding information from the codebook; in AI / machine learning-based CSO compression scenarios, this mapping relationship manifests as mapping the CSO information into a low-dimensional latent vector through the terminal-side encoder model, and then the base station-side decoder decompresses the latent vector to recover the information before compression—this is the case of a two-sided model. Specifically, AI / machine learning-based CSO compression scenarios also include scenarios involving joint source-channel coding or joint coding-modulation. In this scenario, the terminal side uses a projection matrix or dimensionality reduction matrix to compress the CSO information, and the base station side uses a machine learning model to decompress and recover the compressed information—this is the case of a one-sided model. Furthermore, scenarios involving joint source-channel coding or joint coding-modulation can also adopt a two-sided model deployment approach with both the terminal-side encoder and the base station-side decoder. All of the above scenarios can be summarized as a process of compressing and then decompressing channel state information or channel information. Therefore, for ease of understanding, the codebook, projection matrix, or dimensionality reduction matrix or artificial intelligence model (two-sided model or one-sided model) is referred to as a mapping relationship.

[0006] In this method, the first node determines the information used for downlink channel precoding based on the mapping relationship, and at the same time obtains reference information. The first information associated with the two is sent to the second node, so that the second node can determine whether the current mapping relationship is still applicable to the current channel environment based on the information. The mapping relationship can be updated in a timely manner, thereby improving the accuracy of channel state information feedback.

[0007] In one possible design, the first information is first precoding information, and the reference information is reference precoding information; the second information includes at least one of the following: the difference between the signal power when using the first precoding information and the signal power when using the reference precoding information, the signal power of the difference between the first precoding information and the reference precoding information, the ratio of the signal power when using the first precoding information to the signal power when using the reference precoding information, the difference between the signal-to-noise ratio when using the first precoding information and the signal-to-noise ratio when using the reference precoding information, and the generalized cosine square similarity between the first precoding information and the reference precoding information.

[0008] In this design, the first node measures the difference between the precoded information output by the codebook and the ideal precoded information using multiple quantization methods. The power difference reflects the absolute deviation in signal energy; the signal power of the difference reflects the combined deviation of the amplitude and phase of the two precoded vectors in the signal space; the power ratio reflects the relative matching degree; the signal-to-noise ratio difference reflects the difference in impact on signal quality; and the generalized cosine square similarity reflects the matching degree of the two precoded vectors in spatial direction. Multiple statistical measures evaluate the applicability of the codebook from different dimensions, and the second node can flexibly determine whether the codebook needs to be replaced based on these quantization methods. The replacement mentioned in this invention can be replaced with updating, switching, or rollback.

[0009] In one possible design, the second information indicates whether the second node has changed the first mapping relationship.

[0010] In this design, the first node directly sends the judgment result of whether to change the mapping relationship to the second node. The second node does not need to calculate the statistics itself, which reduces the processing burden of the second node and shortens the response time of the change decision.

[0011] In one possible design, when the second information instructs the second node to change the first mapping relationship, the second information is also used to instruct the second node to send the second mapping relationship.

[0012] In this design, while the first node indicates that the mapping relationship needs to be changed, it also instructs the second node to send an alternative codebook or replacement model. The decision and execution of the change are combined into the same signaling message, which reduces the number of signaling interactions and improves the efficiency of the change.

[0013] In one possible design, the second information includes at least one of the following: first information, reference information, a channel estimation matrix determined based on the second channel measurement information, a precoding vector determined based on the second channel measurement information, a channel autocorrelation matrix determined based on the second channel measurement information, and the true value of the first channel measurement information.

[0014] In this design, the first node sends the raw information to the second node, which then compares and makes its own judgments. By sending the first information and the reference information, the second node can directly compare the differences between the two. By sending the channel estimation matrix, precoding vector, channel autocorrelation matrix, or true values, the second node can perform independent calculations and comprehensive judgments based on the raw data at the channel level, providing greater decision-making flexibility. It can also combine other information from the network side to make more accurate replacement decisions.

[0015] In one possible design, the reference information is reference precoding information, the first mapping relationship is the first codebook, and obtaining the reference information corresponding to the first channel measurement information includes: determining the reference precoding information based on all or part of the basis vectors of the first codebook; or determining the reference precoding information based on the second channel measurement information.

[0016] In this design, reference precoding information can be obtained in two ways: one is to use all or part of the codebook's own basis vectors as a reference to achieve an internal evaluation of the codebook's accuracy, which has low computational complexity; the other is to directly calculate the theoretically optimal precoding based on channel state information as a reference benchmark, which has higher evaluation accuracy. These two methods are suitable for different computational complexity and evaluation accuracy requirements, providing a flexible approach to obtaining reference information.

[0017] In one possible design, the first mapping relationship is the first artificial intelligence model (one-sided or two-sided model, or projection matrix), the first information is the latent vector, and the reference information is the true value of the first channel measurement information.

[0018] In this design, the codebook applicability evaluation scheme is extended to precoding determination scenarios based on artificial intelligence models. The artificial intelligence model outputs latent vectors as precoding information based on channel state information, and the reference information uses the true values ​​of the channel state information as a benchmark. By comparing the differences between the latent vectors output by the artificial intelligence model and the true values, the applicability of the artificial intelligence model under the current channel conditions can be evaluated, ensuring that the artificial intelligence-based precoding scheme can trigger model backoff or switching in a timely manner when the channel environment changes.

[0019] In one possible design, the method further includes: receiving third information, which instructs the first node to send second information based on the first information and / or reference information.

[0020] In this design, the second node configures relevant parameters for mapping relationship evaluation to the first node through third information. By configuring the third information, the second node can flexibly control the evaluation behavior of the first node, such as specifying whether the first node reports judgment results, calculation results, or original information, and whether to monitor all layers of the codebook or a specific layer, thus adapting to evaluation needs in different scenarios.

[0021] In one possible design, the method further includes: receiving fourth information, which enables or disables the first node from sending second information based on the first information and reference information.

[0022] In this design, the first node enables or disables the mapping relationship evaluation function under the instruction of the second node. Through the enable and disable control of the fourth information, the first node only performs the evaluation and reports the second information when needed by the second node, avoiding unnecessary continuous monitoring calculations and saving the first node's computing resources and energy consumption. Simultaneously, the second node can flexibly control the first node's evaluation behavior at appropriate times based on network-side scheduling information, channel change trends, or load conditions. In one possible design, the reference information is channel attribute information, which includes at least one of the following: time-domain channel attributes between the first node and the second node, frequency-domain channel attributes between the first node and the second node, or spatial channel attributes between the first node and the second node. The channel attribute information is calculated based on second channel measurement information. The second information is sent based on the reference information, including: sending the second information when the channel attribute information does not meet the first condition; or sending the second information when the number of times the channel attribute information does not meet the first condition exceeds a preset number within a preset time.

[0023] In this design, the first node uses channel attribute information as reference information and determines whether the channel environment has changed significantly by checking if the channel attribute information meets a first condition. When the channel attribute information does not meet the first condition, it indicates that the long-term statistical characteristics of the channel have changed significantly. Continuing to use the current mapping relationship will lead to a decrease in the accuracy of the channel state information feedback or distortion of the model or projection matrix output. At this time, the first node sends a second piece of information to trigger a mapping relationship change. By using a judgment method based on the long-term statistical characteristics of the channel, unnecessary mapping relationship switching caused by short-term channel fluctuations can be reduced, improving the stability and reliability of mapping relationship change judgment.

[0024] In one possible design, the method further includes: receiving fifth information, which is used to enable or disable the first node to determine whether the channel attribute information meets the first condition.

[0025] In this design, the fifth message acts as a switch to control whether the first node performs a first conditional judgment on channel attribute information. When the fifth message indicates enable, the first node begins monitoring and judging channel attribute information; when the fifth message indicates disable, the first node stops judging channel attribute information and does not send the second message. Through the enable and disable control of the fifth message, the second node can flexibly manage the CPI monitoring behavior of the first node, avoiding unnecessary computational overhead when monitoring is not required, and further saving the energy consumption of the first node.

[0026] In one possible design, after sending the second information, the method further includes: determining the sixth information based on a predefined method, the sixth information being used for downlink channel precoding; or, determining the sixth information corresponding to the first channel measurement information based on a third mapping relationship, the third mapping relationship being a mapping relationship built into the first node, the sixth information being used for downlink channel precoding; and sending the sixth information.

[0027] In this design, after the first node reports that the current mapping relationship is not working properly, it can determine the information for downlink channel precoding based on a predefined method or a built-in mapping relationship. By immediately switching to the alternative scheme after reporting the second information, the first node avoids continuing to use the abnormal mapping relationship to calculate precoding information during the waiting period, which would lead to inaccurate channel state information being reported. This avoids the system performance loss caused by the second node scheduling based on inaccurate channel state information.

[0028] In one possible design, determining the sixth information based on a predefined method includes at least one of the following methods: determining the sixth information corresponding to the first channel measurement information based on a fourth mapping relationship, where the fourth mapping relationship is a pre-configured mapping relationship; determining the sixth information corresponding to the first channel measurement information based on a third mapping relationship, where the third mapping relationship is a mapping relationship built into the first node; updating the first mapping relationship, and determining the sixth information corresponding to the first channel measurement information based on the updated first mapping relationship.

[0029] This design provides several predefined transition schemes. The fourth mapping relationship is a pre-configured alternative codebook or model, or an alternative projection matrix. The first node can directly switch to the pre-configured alternative scheme when the current mapping relationship is abnormal, ensuring the continuity of precoding information. The third mapping relationship is a built-in mapping relationship of the first node, always available as a fallback solution, providing basic precoding computation capabilities under any circumstances without additional configuration. Updating the first mapping relationship allows the first node to locally adjust the current mapping relationship to adapt to changes in the channel environment. These multiple predefined methods provide flexible transition options to meet the needs of different scenarios.

[0030] In one possible design, the method further includes sending a seventh message, which is used to indicate the identification information of the mapping relationship used by the first node to determine the sixth message.

[0031] In this design, the first node informs the second node of the specific mapping relationship used to calculate the sixth information through the seventh information. This allows the second node to know the actual mapping relationship used by the first node and to correctly decode the sixth information and reconstruct the channel state information using the corresponding decoding method. This ensures the accuracy and continuity of downlink channel precoding and avoids decoding errors and system performance loss caused by inconsistencies in the mapping relationship between the first and second nodes.

[0032] In a second aspect, a method for a second node in wireless communication is provided. The method includes: receiving second information, which is transmitted based on reference information corresponding to first information and second channel measurement information, wherein the first information is used for downlink channel precoding and is determined by the first node based on the first channel measurement information and a first mapping relationship; and determining whether to change the first mapping relationship or whether the first mapping relationship is working properly based on the second information.

[0033] In this design, the second node receives the mapping relationship evaluation information reported by the first node, and determines whether the current mapping relationship needs to be changed or whether there is an anomaly based on the information, thereby realizing unified management of the mapping relationship, which helps to update the codebook and improve the accuracy of channel state information feedback.

[0034] In one possible design, the first information is first precoding information, and the reference information is reference precoding information; the second information includes at least one of the following: the difference between the signal power using the first precoding information and the signal power using the reference precoding information; the ratio of the signal power using the first precoding information to the signal power using the reference precoding information; the difference between the signal-to-noise ratio using the first precoding information and the signal-to-noise ratio using the reference precoding information; and the generalized cosine squared similarity between the first precoding information and the reference precoding information. In one possible design, the second information indicates whether the first mapping relationship should be changed.

[0035] In one possible design, the second information includes at least one of the following: first information, reference information, a channel estimation matrix determined based on the second channel measurement information, a precoding vector determined based on the second channel measurement information, a channel autocorrelation matrix determined based on the second channel measurement information, and the true value of the first channel measurement information.

[0036] In one possible design, determining whether to change the first mapping relationship based on the second information includes: determining whether to change the first mapping relationship based on at least one of the following: first information, reference information, channel estimation matrix determined based on the second channel measurement information, precoding vector determined based on the second channel measurement information, channel autocorrelation matrix determined based on the second channel measurement information, and the true value of the first channel measurement information.

[0037] In one possible design, the method further includes: sending third information to the first node, the third information being used to instruct the first node to send second information based on the first information and / or reference information.

[0038] Thirdly, a method for a first node in wireless communication is provided. The method includes: obtaining a reference value of channel attribute information between the first node and a second node; obtaining first channel attribute information, which is associated with a first mapping relationship; and sending eighth information based on the first channel attribute information and the reference value of channel attribute information, wherein the eighth information is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0039] It can be understood that the codebook, the channel state information compression model based on artificial intelligence / machine learning, and the projection matrix in joint source-channel coding modulation are essentially all mapping relationships: the first node determines the information used for downlink channel precoding based on the channel state information through this mapping relationship. In the codebook scenario, this mapping relationship manifests as selecting the optimal precoding information from the codebook; in the channel state information compression scenario based on artificial intelligence / machine learning, this mapping relationship manifests as mapping the channel state information into a low-dimensional latent vector through the encoder model. Therefore, for ease of understanding, the codebook or artificial intelligence model is referred to as a mapping relationship.

[0040] In this design, the first node acquires channel attribute information and reference values ​​associated with the current mapping relationship, and determines whether the mapping relationship needs to be updated based on changes in both. This method evaluates the applicability of the mapping relationship from the perspective of long-term changes in the channel environment. When significant changes occur in the channel environment, it helps to trigger timely changes in the mapping relationship, thereby improving the accuracy of channel state information feedback.

[0041] In one possible design, the eighth information includes the difference between the first channel attribute information and the channel attribute information reference value.

[0042] In this design, the first node directly reports the difference between the current channel attribute information and the reference value in the eighth information to the second node. The second node can then directly determine the degree of change in the channel environment based on this difference. Presenting the core quantitative indicators on which the judgment is based directly helps reduce the processing and computational overhead of the second node.

[0043] In one possible design, the eighth information includes at least one of the following: first channel attribute information, and channel attribute information reference value.

[0044] In this design, the first node sends the original current channel attribute information and reference value to the second node, which can then calculate the difference and make its own judgment. By sending the original value, the second node can not only determine whether the current mapping relationship is applicable, but also perform a comprehensive analysis by combining the channel attribute information of other terminals or the channel statistics data from the network side, which helps to improve the flexibility of judgment and the accuracy of decision-making.

[0045] In one possible design, the eighth information indicates whether the second node has changed the first mapping relationship or whether the first mapping relationship is working properly, or whether the first channel attribute information does not meet the preset conditions.

[0046] In this design, the eighth piece of information can carry the first node's self-judgment result regarding the applicability of the mapping relationship, or it can be used to indicate that the first channel attribute information itself no longer meets the preset conditions. The first node can either report the direct judgment conclusion from the terminal side to reduce the processing complexity of the second node, or it can report the state change of the channel attribute information to prompt the second node that the channel environment has become abnormal. Both methods provide the second node with an effective decision-making basis, which helps to flexibly select the reporting strategy in different scenarios.

[0047] In one possible design, when the eighth message indicates a change in the first mapping relationship or when the first mapping relationship is not working properly, the eighth message is also used to instruct the second node to send the second mapping relationship.

[0048] In this design, when the first node indicates that the first mapping relationship needs to be changed, it simultaneously recommends the second mapping relationship to the second node. The decision to change and the execution suggestion are combined into the same signaling message, which helps to reduce the number of signaling interactions and improve the efficiency of the change.

[0049] In one possible design, when the eighth message indicates whether the second node has changed the first mapping relationship or whether the first mapping relationship is working properly, the method includes: sending the eighth message when the difference between the first channel attribute information and the channel attribute information reference value does not meet the second condition; or, sending the eighth message when the number of times the difference between the first channel attribute information and the channel attribute information reference value does not meet the second condition exceeds a preset number within a preset time.

[0050] In this design, the first node uses the difference between the first channel attribute information and the reference value as the judgment standard, compares the difference with the second condition, and sends the eighth message when the difference does not meet the second condition, or when the number of times the difference fails to meet the second condition within a preset time window reaches a preset number. By setting the second condition and the number threshold for dual filtering, it helps to avoid frequent reporting caused by short-term channel jitter, reduces unnecessary signaling overhead, and ensures reliable reporting when the channel environment undergoes substantial changes.

[0051] In one possible design, the channel attribute information includes at least one of the following: time-domain channel attributes between the first node and the second node, frequency-domain channel attributes between the first node and the second node, or spatial-domain channel attributes between the first node and the second node.

[0052] In this design, monitoring changes in channel attributes across three dimensions—time, frequency, and spatial—helps to comprehensively capture changes in the channel environment across different dimensions. Time-domain channel attributes reflect changes in channel correlation over time, frequency-domain channel attributes reflect changes in channel correlation over frequency, and spatial-domain channel attributes reflect changes in channel correlation over space. This multi-dimensional monitoring helps to more accurately determine whether the channel environment has undergone substantial changes, thereby facilitating a more reliable assessment of the applicability of the mapping relationship.

[0053] In one possible design, the method further includes: receiving a ninth message, which instructs the first node to send an eighth message based on the first channel attribute information and the channel attribute information reference value.

[0054] In this design, the first node monitors and reports channel attribute information under the instruction of the second node. The second node can send relevant parameters for monitoring channel attribute information (such as the second condition, the preset time window length, etc.) to the first node through the ninth information, realizing the on-demand configuration of the monitoring process and monitoring parameters. This helps the second node to flexibly manage the channel attribute information monitoring behavior of the first node, avoid unnecessary computational overhead when monitoring is not required, and save energy consumption of the first node.

[0055] Fourthly, a method for a second node in wireless communication is provided, the method comprising: receiving eighth information, the eighth information being transmitted based on first channel attribute information and a channel attribute information reference value, the first channel attribute information being associated with a first mapping relationship; and determining, based on the eighth information, whether to change the first mapping relationship or whether the first mapping relationship is working properly.

[0056] This communication method can be applied to a second node. For example, it can be executed by the second node itself, or by a chip, chip system, processor, processor system, circuit unit, or circuit system applied to the second node. For ease of description, the following content in this section will use the second node as an example.

[0057] In this design, the second node receives evaluation information sent by the first node based on changes in channel attribute information, and determines whether the mapping relationship needs to be changed accordingly. This method evaluates the applicability of the mapping relationship from the perspective of long-term changes in the channel environment. When the channel environment changes significantly, it helps to trigger the mapping relationship change in a timely manner, thereby improving the accuracy of channel state information feedback.

[0058] In one possible design, the eighth information includes the difference between the first channel attribute information and the channel attribute information reference value.

[0059] In one possible design, the eighth information includes at least one of the following: first channel attribute information, and channel attribute information reference value.

[0060] In one possible design, the eighth message indicates whether the first mapping relationship has been replaced or whether the first mapping relationship is working properly.

[0061] In one possible design, when the eighth message indicates a change in the first mapping relationship or when the first mapping relationship is not working properly, the eighth message is also used to instruct the second node to send the second mapping relationship.

[0062] In one possible design, when determining to change the first mapping relationship, the method also includes: sending the second mapping relationship.

[0063] In one possible design, the channel attribute information includes at least one of the following: time-domain channel attributes between the first node and the second node, frequency-domain channel attributes between the first node and the second node, or spatial-domain channel attributes between the first node and the second node.

[0064] In one possible design, the method further includes: sending a ninth message to the first node, the ninth message being used to instruct the first node to send an eighth message based on the first channel attribute information and the channel attribute information reference value.

[0065] Fifthly, a first node is provided, including a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to invoke the computer programs in the memory to cause the first node to perform some or all of the steps described in the method of the first aspect above.

[0066] In a sixth aspect, a second node is provided, including a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to invoke the computer programs in the memory to cause the second node to perform some or all of the steps described in the method of the second aspect above.

[0067] Seventhly, embodiments of this application provide a communication system including the aforementioned communication device. In another possible design, the system may further include other devices that interact with the communication device as described in the embodiments of this application.

[0068] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps in the methods described above.

[0069] Ninthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of the methods described in the foregoing aspects. In some implementations, the computer program product may be a software installation package.

[0070] In a tenth aspect, embodiments of this application provide a chip including a memory and a processor, the processor being able to call and run a computer program from the memory to implement some or all of the steps described in the methods of the foregoing aspects.

[0071] In the eleventh aspect, embodiments of this application provide a chip module including a memory and a processor, wherein the processor can call and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.

[0072] In a twelfth aspect, embodiments of this application provide a communication device, the chip including a memory and a processor, the processor being able to call and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.

[0073] In this embodiment, the first node determines whether the first mapping relationship is still applicable based on the comparison result between the first information and the reference information. When the performance of the mapping relationship deteriorates, the first node reports the second information to the second node to trigger the mapping relationship replacement. By using the precoding information output by the mapping relationship and the reference information for difference quantization on the first node side, the first node can pre-determine whether the mapping relationship is normal before the second node actually uses the current mapping relationship to schedule downlink data. This helps to realize the early detection and timely replacement of the mapping relationship when it is not applicable, and avoids the system performance loss caused by the second node using inaccurate channel state information for scheduling. Attached Figure Description

[0074] Figure 1A This application provides a schematic diagram of the architecture of a communication system. Figure 1B This is a schematic diagram of the architecture of another communication system provided in an embodiment of this application; Figure 1C This is a schematic diagram of the architecture of another communication system provided in an embodiment of this application; Figure 2A and Figure 2B A schematic diagram of the wireless protocol stack structure provided in this application; Figure 3 A flowchart illustrating a communication method provided in an embodiment of this application; Figure 4 A flowchart illustrating another communication method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a terminal device provided in another embodiment of this application; Figure 6 This is a schematic diagram of the structure of a network device provided in another embodiment of this application; Figure 7 This is a schematic diagram of the structure of a communication device provided in another embodiment of this application; Figure 8 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0075] Communication system architecture The technical solutions of this application embodiment can be applied to various communication systems, such as: Global System for Mobile Communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, evolution of NR system, LTE-based access to unlicensed spectrum (LTE-U) system, NR-based access to unlicensed spectrum (NR-U) system, non-terrestrial network (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), and Wireless Fidelity (WF). Fidelity (WiFi), 5th-generation (5G) communication systems or other communication systems, such as future communication systems, such as 6th-generation mobile communication systems, or satellite communication systems.

[0076] Traditional communication systems typically support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication but also, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to these communication systems.

[0077] The communication system in this application embodiment can be applied to carrier aggregation (CA) scenarios, dual connectivity (DC) scenarios, and standalone (SA) network deployment scenarios.

[0078] The communication system in this application embodiment can be applied to unlicensed spectrum, which can also be considered as shared spectrum; or, the communication system in this application embodiment can also be applied to licensed spectrum, which can also be considered as dedicated spectrum.

[0079] The embodiments of this application can be applied to non-terrestrial network (NTN) systems as well as terrestrial network (TN) systems. By way of example and not limitation, NTN systems include NR-based NTN systems and IoT-based NTN systems.

[0080] This application describes various embodiments in conjunction with network devices and terminal devices. The terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment, etc.

[0081] In the embodiments of this application, the terminal device may be a station (ST) in a WLAN, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle, an in-vehicle device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved public land mobile network (PLMN) network, etc.

[0082] In the embodiments of this application, the terminal device can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as handheld devices with wireless connectivity, in-vehicle devices, etc. The terminal device in the embodiments of this application can be a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. Optionally, the terminal device can be used to act as a base station. For example, the terminal device can act as a scheduling entity, providing sidelink signals between terminal devices in V2X or D2D, etc. For example, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices can communicate without relaying communication signals through base stations.

[0083] In the embodiments of this application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships); and it can also be deployed in the air (such as airplanes, balloons and satellites).

[0084] In the embodiments of this application, the terminal device may be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical care, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, or wireless terminal device in smart home, etc. The terminal device involved in the embodiments of this application may also be referred to as a terminal, user equipment (UE), access terminal device, vehicle-mounted terminal, industrial control terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal device, mobile device, UE, wireless communication device, UE agent, or UE device, etc. The terminal device may also be fixed or mobile.

[0085] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0086] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, transmitting and receiving point (TRP), transmitting point (TP), master MeNB, secondary SeNB, multi-mode radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. Base stations can also be mobile switching centers, devices that perform base station functions in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, network-side devices in 6G networks, and devices that perform base station functions in future communication systems. Base stations can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0087] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0088] In some deployments, the network device in this application embodiment may refer to a CU or a DU, or the network device may include both a CU and a DU. The gNB may also include an AAU.

[0089] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located.

[0090] By way of example and not limitation, in the embodiments of this application, the network device may have mobility characteristics; for example, the network device may be a mobile device. In some embodiments of this application, the network device may be a satellite or a balloon station. For example, the satellite may be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a highly elliptical orbit (HEO) satellite, etc. In some embodiments of this application, the network device may also be a base station located on land, water, or other similar locations.

[0091] In this embodiment of the application, the network device can provide services for a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell here can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0092] For example, Figure 1A This is a schematic diagram of the architecture of a communication system provided in an embodiment of this application. Figure 1A As shown, the communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or a communication terminal, terminal). The network device 110 can provide communication coverage for a specific geographical area and can communicate with terminal devices located within that coverage area.

[0093] Figure 1A An exemplary diagram shows a network device and two terminal devices. In some embodiments of this application, the communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area. This application does not limit the scope of the embodiments.

[0094] For example, Figure 1B This is a schematic diagram of the architecture of another communication system provided in an embodiment of this application. Please refer to... Figure 1B This includes terminal device 1101 and satellite 1102, which can communicate wirelessly. The network formed between terminal device 1101 and satellite 1102 can also be called an NTN. Figure 1B In the architecture of the communication system shown, satellite 1102 can function as a base station, and terminal device 1101 and satellite 1102 can communicate directly. In this system architecture, satellite 1102 can be referred to as a network device. In some embodiments of this application, the communication system may include multiple network devices 1102, and the coverage area of ​​each network device 1102 may include other numbers of terminal devices; this application does not limit this aspect.

[0095] For example, Figure 1C This is a schematic diagram of the architecture of another communication system provided in an embodiment of this application. Please refer to... Figure 1C The network includes terminal device 1201, satellite 1202, and base station 1203. Terminal device 1201 and satellite 1202 can communicate wirelessly, and satellite 1202 can communicate with base station 1203. The network formed by terminal device 1201, satellite 1202, and base station 1203 can also be called an NTN. Figure 1C In the architecture of the communication system shown, satellite 1202 may not function as a base station, and communication between terminal device 1201 and base station 1203 requires relay through satellite 1202. In this system architecture, base station 1203 can be referred to as a network device. In some embodiments of this application, the communication system may include multiple network devices 1203, and the coverage area of ​​each network device 1203 may include other numbers of terminal devices; this application does not limit this aspect.

[0096] It should be noted that, Figures 1A-1C This application is merely an example illustrating the system to which this application applies. Of course, the methods shown in the embodiments of this application can also be applied to other systems, such as 5G communication systems, LTE communication systems, etc. This application does not specifically limit these systems.

[0097] In some embodiments of this application, Figures 1A-1C The wireless communication system shown may also include other network entities such as a mobility management entity (MME) and an access and mobility management function (AMF), but this application does not limit this.

[0098] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Figure 1A Taking the communication system 100 shown as an example, the communication equipment may include a network device 110 and a terminal device 120 with communication functions. The network device 110 and the terminal device 120 may be the specific devices described above, which will not be repeated here. The communication equipment may also include other devices in the communication system 100, such as network controllers, mobility management entities and other network entities. This application embodiment does not limit this.

[0099] Wireless Protocol Stack Figure 2A and Figure 2B The following are schematic diagrams of the wireless protocol stack structure of one embodiment of this application. Figure 2A and Figure 2B This introduction uses the 5G wireless protocol stack as an example. The 5G wireless protocol stack is divided into two planes: the user plane (UP) protocol stack and the control plane (CP) protocol stack. The user plane protocol stack contains the protocol suite used for user data transmission, while the control plane protocol stack contains the protocol suite used for control signaling transmission in the 5G system. The specific names of each protocol stack layer are as follows: like Figure 2A As shown, the user plane protocol stack, from top to bottom, includes: the Service Data Adaptation Protocol (SDAP) layer, the Packet Data Convergence Protocol (PDCP) layer, the Radio Link Control (RLC) layer, the Medium Access Control (MAC) layer, and the Physical (PHY) layer. The SDAP layer is optional and is not present in LTE.

[0100] like Figure 2B As shown, the control plane protocol stack, from top to bottom, includes: non-access stratum (NAS); radio resource control (RRC) layer, PDCP layer, RLC layer, MAC layer, and PHY layer.

[0101] It should be understood that the different layers in the above protocol stack have different functions, and they work together through inter-layer interaction to achieve communication between terminal devices and network devices. With the development of artificial intelligence technology, AI-assisted computing has permeated the processing implementation methods of the above protocol stack. For example, the scheduling algorithm of the MAC layer and the encoding / decoding algorithm of the PHY layer can apply artificial intelligence algorithms to improve the performance of communication algorithms.

[0102] As an example, Figure 2A and Figure 2B The wireless protocol architecture described herein is applicable to the first node in this application.

[0103] As an example, Figure 2A and Figure 2B The wireless protocol architecture described herein is applicable to the second node in this application.

[0104] It should be understood that some functionalities in a wireless protocol architecture can also be implemented in one or more devices. For example, the functions of different layers in the control plane protocol stack can be implemented by multiple nodes on the network side.

[0105] It should be understood that the interpretation of the terminology in the embodiments of this application may refer to the TS36, TS37 and TS38 series of specifications of the 3rd generation partnership project (3GPP), but may also refer to the specifications of the Institute of Electrical and Electronics Engineers (IEEE).

[0106] To facilitate understanding, some related technical knowledge involved in the embodiments of this application is first introduced. The following related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0107] In the aforementioned communication system, the terminal device reports channel state information to the network device via a wireless link, and the network device performs downlink scheduling based on the channel state information reported by the terminal device. The accuracy of the channel state information feedback directly affects the transmission performance of the communication system. To support multi-antenna transmission technology, the terminal device needs to calculate and report a precoding matrix indicator (PMI) based on a codebook. The codebook defines a set of available precoding vectors. The terminal device selects the precoding vector that best matches the current channel conditions from the codebook and reports the corresponding PMI to the network device. The network device performs downlink data scheduling and beamforming based on the PMI reported by the terminal device.

[0108] Currently, both Type I and Type II codebooks used in 5G systems are of fixed design, with the codebooks already written into the terminal device's storage at the factory. Type I codebooks are constructed by selecting basis vectors from a spatial domain basis set, while Type II codebooks are constructed by jointly selecting basis vectors from both the spatial and frequency domain basis sets. In next-generation communication systems such as 6G, the maximum downlink bandwidth may reach 400MHz, and the number of ports may support 256 or 512, resulting in a significant overhead for terminal devices to calculate channel status information (CSI). To reduce the overhead of terminal CSI calculation, 3GPP is currently discussing a downloadable codebook scheme, whereby the terminal device downloads the codebook from the network equipment and calculates and reports CSI based on this downloadable codebook.

[0109] Downloadable codebooks are designed for specific scenarios, and their basis vector composition typically covers only a portion of the entire possible set of spatial basis vectors. For example, a downloadable codebook may be constructed by selecting a subset of basis vectors from the spatial basis vector set, or by jointly selecting a subset of basis vectors from both the spatial and frequency domain basis vector sets. Therefore, it is only applicable to specific channel environments. When the wireless environment changes or the terminal device's state changes (e.g., a change in movement speed), the currently downloaded codebook may no longer match the current channel conditions, requiring an update to the codebook.

[0110] In 3GPP's research on channel state information (CSI) based on artificial intelligence / machine learning, a scheme was proposed to compress and feed back CSI using a neural network model. Specifically, a neural network model is deployed at either the transmitter or receiver. The receiver (terminal device) obtains CSI based on measurements of the downlink reference signal and inputs this CSI into an encoder model. The encoder model outputs a low-dimensional latent vector, which the terminal device feeds back to the transmitter (network device). Upon receiving the latent vector, the network device reconstructs the CSI using a decoder model for downlink scheduling and beamforming. This scheme significantly reduces the overhead of CSI feedback by compressing high-dimensional CSI into a low-dimensional latent vector for transmission. In 5G systems, the AI-based CSI compression scheme belongs to source coding. The terminal-side encoder model compresses the CSI, while the base station-side decoder model decompresses and recovers the compressed latent vector. This collaborative working mode between the terminal-side encoder and the base station-side decoder is called a two-sided model. In next-generation communication systems such as 6G, to further improve the performance of CSI compression, joint source channel coding (JSCC) or joint source channel coding and modulation (JSCCM) schemes have been proposed. These schemes combine channel coding and even modulation functions on the basis of source coding to improve the overall efficiency of compression and transmission. In JSCC / JSCCM scenarios, model deployment methods include at least one of the following: Method 1, adopting the bilateral model deployment method of 5G, i.e., deploying an encoder on the terminal side and a decoder on the base station side, with both working together to complete the compression and decompression of channel state information; Method 2, adopting a unilateral model deployment method, i.e., deploying a projection matrix or dimensionality reduction matrix on the terminal side to complete the compression of channel state information, and deploying a machine learning model on the base station side to decompress and recover the compressed information.

[0111] However, existing technologies do not address how to determine whether the currently used mapping relationship (such as a codebook or artificial intelligence model) is still applicable, or how to monitor the currently used downloadable codebook or artificial intelligence precoding model to determine whether it needs to be replaced. If a terminal device uses a codebook that no longer matches the current channel state to calculate and report CSI for an extended period, or uses an artificial intelligence model that is no longer suitable for the current channel conditions to output latent vectors for an extended period, network devices will perform scheduling based on inaccurate channel state information, leading to a degraded communication system performance. Those skilled in the art have not provided specific technical solutions for this.

[0112] It should be understood that the following one or more embodiments proposed in this application can respectively solve one or more of the following technical problems: 1. How to determine whether the currently used mapping relationship (such as codebook or artificial intelligence model (one-sided model or two-sided model, or projection matrix) is still applicable to the current channel conditions, so as to avoid network devices scheduling based on inaccurate channel state information, which would lead to a decrease in system performance.

[0113] 2. How to detect mapping mismatch problems in advance and trigger timely replacement by comparing the precoding information output by the mapping relationship with the ideal precoding information on the terminal side.

[0114] 3. How to determine whether the mapping relationship needs to be changed based on changes in the long-term statistical characteristics of the channel, so as to reduce unnecessary switching caused by short-term channel fluctuations.

[0115] Figure 3 The method shown is described from the perspective of interaction between the first node and the second node.

[0116] In some embodiments, the first node can be any type of terminal device mentioned above. The following description will primarily use the UE as the first node.

[0117] In some embodiments, the second node may include access network equipment, such as a base station (also known as a terrestrial base station) or a satellite device that deploys a base station. The following description will primarily use the base station as the second node.

[0118] In other embodiments, the second node can be a core network element, such as an MME or AMF element. Alternatively, the second node can be a gateway device, such as a gateway or a user plane function (UPF) gateway (SGW). This gateway device can also be a call session control function (CSCF) entity.

[0119] Figure 3 The communication process shown includes S301 to S304.

[0120] S301, the first node determines the first information corresponding to the first channel measurement information based on the first mapping relationship, and the first information is used for downlink channel precoding.

[0121] The first mapping relationship is used to determine the information for downlink channel precoding based on the channel state information. The first mapping relationship includes at least one of the following: a first codebook, a first artificial intelligence model, or a first projection matrix; the channel measurement information includes channel state information, such as a channel estimation matrix, a precoding vector, a channel autocorrelation matrix, etc.

[0122] When the first mapping relationship is the first codebook, the first codebook can be sent from the second node to the first node via radio resource control (RRC) signaling or media access control (MAC) control element (CE). The first codebook contains one or more basis vectors, which the first node uses to construct a precoding vector set for calculating and selecting the precoding matrix indication (PMI). Optionally, the second node sends an activation signaling to the first node, and the first node only begins using the first codebook for PMI calculation after receiving the activation signaling. Optionally, the first codebook is considered to be in use as soon as it is downloaded, and the first node does not need additional activation signaling. Optionally, the first node begins monitoring the first codebook as soon as it is deployed or activated, without the second node needing to send additional signaling to start monitoring. The first node continuously reports monitoring content according to the configuration while using the first codebook, until the first node falls back to a specified codebook or switches to another codebook, at which point the monitoring process for the first codebook stops. Accordingly, after acquiring the first codebook, the first node obtains the first channel measurement information based on the measurement of the downlink reference signal, and selects the precoding vector that best matches the current channel conditions from the set of basis vectors contained in the first codebook to determine the corresponding first information. At this time, the first information is the first precoding information, which can be a PMI or a specific precoding vector.

[0123] When the first mapping relationship is the first artificial intelligence model, the first artificial intelligence model can be sent from the second node to the first node via RRC signaling or MAC-CE, or via a non-over-the-air (non-OTA) method. The first artificial intelligence model can include an encoder model and a decoder model. The first node deploys the encoder model, and the second node deploys the decoder model. The first node obtains first channel measurement information based on measurements of the downlink reference signal and inputs this information into the encoder model. The encoder model outputs a latent vector as the first information. The first node feeds back the latent vector to the second node, which reconstructs the channel state information using the decoder model for downlink scheduling and beamforming. Optionally, the encoder and decoder models of the first artificial intelligence model are trained based on a specific channel environment. When the wireless environment changes, the latent vector output by the model may no longer be applicable to the current channel conditions.

[0124] S302, the first node obtains the reference information corresponding to the second channel measurement information.

[0125] The reference information is used to measure the ideal baseline under a given channel state. Depending on the first mapping relationship, the first node obtains the reference information in different ways: the second channel measurement information and the aforementioned first channel measurement information are measurement results of the same wireless channel, and they may be obtained at different times or under different conditions. For example, the first channel measurement information may be channel state information obtained by the first node at the current moment based on measurements of the downlink reference signal, while the second channel measurement information may be channel state information obtained by the first node at another moment based on measurements of the same downlink reference signal, or channel state information obtained by the second node based on network-side measurements. Optionally, the first channel measurement information and the second channel measurement information may be the same set of channel measurement data. The channel measurement information includes channel state information, such as the channel estimation matrix, precoding vector, channel autocorrelation matrix, etc.

[0126] In some implementations, when the first mapping relationship is the first codebook, the reference information is the reference precoding information, and the first node can obtain the reference precoding information in the following ways: Method 1: Determine reference precoding information based on all or part of the basis vectors of the first codebook. Specifically, the first node traverses all or part of the basis vectors constituting the first codebook, calculates the expected performance index (such as signal power or signal-to-noise ratio) for each candidate precoding vector under the current channel estimation result, and selects the precoding vector that maximizes the system capacity or minimizes the mean square error as the reference precoding information. In this method, the candidate range of reference precoding information is limited to the basis vector set corresponding to the first codebook, and the computational complexity is relatively low.

[0127] Method 2: Determine reference precoding information based on second channel measurement information. Specifically, the first node obtains the channel estimation matrix based on measurements of the downlink reference signal. By performing singular value decomposition or eigenvalue decomposition on the channel estimation matrix, it obtains the ideal precoding vector that maximizes system capacity or minimizes mean square error under a given channel condition, which serves as the reference precoding information. The reference precoding information in this method is not limited by the codebook basis vector set and can reflect the true optimal precoding scheme under the current channel conditions.

[0128] In some implementations, when the first mapping relationship is a first artificial intelligence model, the reference information is the ground truth of the first channel measurement information. Specifically, the first node obtains a channel estimation matrix based on the measurement of the downlink reference signal, and this channel estimation matrix is ​​the ground truth of the first channel measurement information.

[0129] S303, the first node sends second information based on the first information and / or reference information, the second information being used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0130] It should be understood that the replacement of the first mapping relationship in the embodiments of this application may have, but is not limited to, the following meanings depending on the different types of the first mapping relationship: When the first mapping relationship is a codebook, "replacement" can refer to replacing the currently used downloadable codebook with another codebook, or updating the currently used downloadable codebook, such as adjusting the range of basis vector selection, the number of basis vectors, or the combination method of basis vectors in the codebook. In one example, the second node sends a new downloadable codebook to the first node to replace the current codebook, or the second node sends update parameters to the first node to perform a partial update to the current codebook. Alternatively, it can revert to a pre-defined codebook.

[0131] When the first mapping relationship is an artificial intelligence model, "replacement" can refer to switching the currently used artificial intelligence model to another model, such as switching from the current encoder-decoder model pair to another pre-configured encoder-decoder model pair, or switching the current model to an alternative model trained on a different training dataset or with a different network architecture. In one example, the second node sends new artificial intelligence model parameters or model identifiers to the first node, and the first node loads the corresponding alternative model based on the parameters or identifiers.

[0132] Optionally, depending on the content of the second information, the behavior of the first node may include at least one of the following: Method 1: The first node determines whether the first mapping relationship needs to be changed and sends the determination result as the second information.

[0133] When the first mapping relationship is the first codebook, the first node compares the first precoding information with the reference precoding information, and determines whether the first codebook is still applicable by quantifying the degree of difference between the two. The first node can calculate at least one of the following statistics as a basis for comparison: (1) The difference between the signal power when using the first precoding information and the signal power when using the reference precoding information, i.e., ||HW1||² - ||HW2||² or ||HW2||² - ||HW1||², where H is the channel estimation matrix, W1 is the precoding vector corresponding to the first precoding information, and W2 is the precoding vector corresponding to the reference precoding information; (2) The ratio of the signal power when using the first precoding information to the signal power when using the reference precoding information, i.e., ||HW1||² / ||HW2||²; (3) The signal power of the difference between the first precoding information and the reference precoding information, i.e., ||HW1 - HW2||²; (4) The difference between the signal-to-noise ratio when using the first precoding information and the signal-to-noise ratio when using the reference precoding information; (5) The generalized cosine square similarity between the first precoding information and the reference precoding information, or the mean of the generalized cosine square similarity of each layer.

[0134] The first node can calculate the above statistics within a preset time window. If the number of times a certain statistic fails to meet a preset threshold exceeds a preset number, the first codebook is determined to be unsuitable and needs to be replaced. For example, the first node calculates ||HW1||² - ||HW2||². If the number of times this difference exceeds a predefined threshold within the preset time window exceeds N times, the first codebook is considered to be malfunctioning in the current wireless environment. Optionally, for different statistics, the judgment condition includes at least one of the following: the statistic is greater than a preset threshold, the statistic is greater than or equal to a preset threshold, the statistic is less than a preset threshold, or the statistic is less than or equal to a preset threshold. For example, for the power ratio ||HW1||² / ||HW2||², if this ratio is less than a predefined threshold, it indicates that the codebook output power loss relative to the ideal value is too large, and the first codebook is considered to be malfunctioning.

[0135] Optionally, the first node can also compare the statistics of each layer separately, or calculate the average of all layers and then compare them. Specifically, when the first precoding information and the reference precoding information are multi-layer precoding, each layer corresponds to a precoding vector.

[0136] For example, the first node calculates the aforementioned statistics for each layer and compares them with preset thresholds. For instance, for the l-th layer, it calculates ||Hl·W1l||² - ||Hl·W2l||², where Hl is the channel estimate corresponding to the l-th layer, W1l is the precoding vector corresponding to the l-th layer in the first precoding information, and W2l is the precoding vector corresponding to the l-th layer in the reference precoding information. When the statistics of the l-th layer do not meet the preset threshold, the codebook basis vector corresponding to that layer is considered no longer applicable. The first node can set preset thresholds independently for each layer, or it can share the same preset threshold for all layers. Optionally, the first node can determine that the first codebook is no longer applicable when the statistics of any layer do not meet the preset threshold; or, the first node only determines that the first codebook is no longer applicable when the statistics of all layers do not meet the preset threshold. Alternatively, for layers that need updating or are malfunctioning in the second information reporting, only the codebook or mapping matrix of one or more layers is updated.

[0137] For example, the first node sums or averages the statistics of all layers and compares the result with a preset threshold. For instance, it calculates the average signal power difference of all layers, i.e., (1 / L)·Σ||Hl·W1l||² - ||Hl·W2l||², where L is the number of layers. When this average value exceeds the preset threshold, it is determined that the first codebook is no longer applicable.

[0138] When the first mapping relationship is the first artificial intelligence model, the first node compares the latent vector output by the artificial intelligence model with the true value of the first channel measurement information. For example, the first node can calculate the mean squared error (MSE) or cosine similarity between the channel state information reconstructed by decoding the latent vector and the true value. When the reconstruction error exceeds a preset threshold, it is determined that the first artificial intelligence model is no longer suitable for the current channel conditions and needs to be replaced (model switching or rollback).

[0139] In this method, the first node sends the judgment result as the second information, such as a 1-bit indicator, where a value of 1 indicates that a replacement is needed and a value of 0 indicates that a replacement is not needed. The second node directly decides whether to perform the replacement based on the judgment result of the first node. Alternatively, if the codebook of a certain layer needs to be replaced, that layer is indicated. This can be a bitmap, such as an 8-bit bitmap 00010000 indicating that the fourth layer needs to be replaced, or a 3-bit binary code 011 indicating that the codebook of the fourth layer needs to be replaced.

[0140] Optionally, when the first node indicates that the first mapping relationship needs to be changed, it may also carry a suggested new codebook identifier, codebook pairing identifier, or new model identifier in the second information to implicitly inform the second node that the first mapping relationship is no longer applicable and suggest switching to a new mapping relationship.

[0141] In Method Two, the first node calculates the corresponding results based on the statistical quantities or error calculation methods described in Method One. These include, for example, the difference between the signal power using the first precoding information and the signal power using the reference precoding information, the signal power of the difference between the first and reference precoding information, the ratio of the signal power using the first precoding information to the signal power using the reference precoding information, the difference between the signal-to-noise ratio using the first and reference precoding information, and the generalized cosine squared similarity between the first and reference precoding information. The first node then sends these calculation results as second information to the second node, which determines whether to change the first mapping relationship based on these results. In this method, the first node performs the calculations but does not determine applicability; the determination process is completed by the second node.

[0142] In Method 3, the first node sends the first information and reference information as the second information to the second node, which then compares and determines whether to change the first mapping relationship. The second information may also include at least one of the following: a channel estimation matrix determined based on the second channel measurement information, a precoding vector determined based on the second channel measurement information, a channel autocorrelation matrix determined based on the second channel measurement information, and the true value of the first channel measurement information. In this method, the first node does not perform applicability judgments, only reporting the original information; the judgment process is completed by the second node. The second node can use the same calculation method as in Method 2, or it can combine other information from the network side for comprehensive judgment, providing greater decision-making flexibility.

[0143] In some implementations, the second node sends third information to the first node. This third information instructs the first node to monitor the mapping relationship based on the first information and / or reference information and then send the second information. For example, the third information may include at least one of the following configuration parameters: preset time window length, predefined threshold, reporting content type, monitoring granularity, and monitoring period. The reporting content type corresponds to the three methods in S303, indicating whether the first node reports the judgment result, calculation result, or original information; the monitoring granularity indicates whether the first node monitors all layers of the codebook or only a specific layer.

[0144] In some implementations, the second node sends a fourth message to the first node, which enables or disables the first node from sending the second message based on the first message and / or reference information.

[0145] For example, when the fourth message indicates enable, the first node starts the mapping relationship evaluation function, performs an applicability evaluation on the first mapping relationship in accordance with the method in S303, and sends the second message when the conditions are met. When the fourth message indicates disable, the first node disables the mapping relationship evaluation function, neither performs the evaluation nor sends the second message.

[0146] It is understood that enabling and disabling in this application refer to the control of opening and closing a certain function or process. Enabling indicates that the second node sends a signaling message to the first node, allowing the first node to start or execute a specific function or process, such as enabling mapping relationship evaluation (enabling codebook update monitoring), enabling CPI-assisted codebook update monitoring, enabling CPI-assisted machine learning model monitoring, etc. Disabling indicates that the second node sends a signaling message to the first node, instructing the first node to stop or close the function or process being executed. Those skilled in the art will understand that enabling and disabling can be implemented in various ways, such as through specific bits in the signaling (e.g., 1 indicates enabling, 0 indicates disabling), or through a timer mechanism (e.g., enabling takes effect within a preset time window, and automatically disabling after timeout), or triggered by the sending and receiving of specific signaling. Optionally, when the second node does not send the fourth information, the first node can default to an enabled or disabled state; the specific default state can be pre-configured by the network side or specified by the standard. Furthermore, the concepts of enabling and disabling also apply to the control of turning the CPI monitoring function on and off in the fifth information section, which will not be elaborated here.

[0147] Optionally, the fourth information can be sent via RRC signaling, MAC-CE, or DCI signaling. Optionally, the fourth information is a 1-bit indicator, with a value of 1 indicating enable and a value of 0 indicating disable.

[0148] Optionally, the first node calculates channel attribute information based on measurements of the downlink reference signal. The channel attribute information includes at least one of the following: time-domain channel property (TDCP) between the first node and the second node, frequency-domain channel property (FDCP) between the first node and the second node, or space-domain channel property (SDCP) between the first node and the second node. Specifically, TDCP reflects the correlation changes of the channel in the time dimension, FDCP reflects the correlation changes of the channel in the frequency dimension, and SDCP reflects the correlation changes of the channel in the spatial dimension.

[0149] As will be understood by those skilled in the art, channel attribute information is a statistical result obtained through at least one measurement in one dimension, used to reflect the changing trend of channel characteristics in that dimension. Specifically, during the use of the first mapping relationship, the first node continuously performs multiple measurements of the channel in a certain dimension, and calculates the channel attribute information for that dimension based on the results of the multiple measurements. For example, in the time domain dimension, the first node measures the channel at multiple time points, and calculates multiple values ​​of the time-domain channel attribute (TDCP) (corresponding to the channel correlation at different time intervals) based on the time-domain channel estimation results of the multiple measurements. The multiple calculated values ​​constitute a vector or sequence, and the current channel condition is judged by the change (trend) of these values. Similarly, in the frequency domain dimension, the first node measures the channel at multiple frequency points or frequency bands, and calculates the frequency-domain channel attribute (FDCP) based on the frequency-domain channel estimation results of the multiple measurements; in the spatial domain dimension, the first node measures the channel in multiple spatial directions or beams, and calculates the spatial channel attribute (SDCP) based on the spatial channel estimation results of the multiple measurements. By performing multiple measurements and calculating multiple numerical statistical results in a single dimension, the first channel attribute information can reflect the long-term trend of channel characteristics in that dimension, rather than the instantaneous value at a certain moment. This helps to more stably and reliably determine whether the channel environment has undergone substantial changes.

[0150] In some implementations, the first node compares the currently measured channel attribute information with a first condition. When the channel attribute information does not meet the first condition, the first node sends second information based on the first information and reference information. Optionally, the first node can also count the number of times the channel attribute information does not meet the first condition within a preset time window. If the number of times it does not meet the first condition exceeds a preset number, then the second information is sent.

[0151] Optionally, the channel attribute information not meeting the first condition includes at least one of the following situations: Taking TDCP as an example, FDCP and SDCP are similar and will not be elaborated further: (1) The channel attribute information does not meet the preset threshold. For example, the value of the channel attribute information is greater than the preset threshold, the value of the channel attribute information is greater than or equal to the preset threshold, the value of the channel attribute information is less than the preset threshold, or the value of the channel attribute information is less than or equal to the preset threshold. Specifically, for TDCP, when the TDCP value is greater than or equal to the preset threshold, it indicates that the time-domain correlation characteristics of the channel have changed significantly, and continuing to use the current mapping relationship will lead to a decrease in the accuracy of the channel state information feedback or distortion of the model output. (2) The change of the channel attribute information exceeds the preset range within a certain period of time. For example, the difference between the TDCP value measured by the first node at the current time and the TDCP value measured at the initial time (such as when the first mapping relationship is used) exceeds the preset range, indicating that the channel environment has undergone significant long-term changes during the period of using the first mapping relationship. (3) The trend of the change of multiple measurements of TDCP within the preset measurement time exceeds the preset value, indicating that the channel environment has undergone significant changes during the period of using the first mapping relationship.

[0152] In some implementations, the first node receives a fifth message sent by the second node. This fifth message enables or disables the first node's determination of whether the channel attribute information meets the first condition. When the fifth message indicates enable, the first node begins monitoring and judging the channel attribute information, comparing the currently measured channel attribute information with the first condition. If the channel attribute information does not meet the first condition, a second message is sent; or if the number of times the channel attribute information fails to meet the first condition exceeds a preset number within a preset time, a second message is sent. When the fifth message indicates disable, the first node stops judging the channel attribute information and does not send a second message.

[0153] Optionally, the fifth message can be sent via RRC signaling or MAC-CE. Optionally, the fifth message is a 1-bit indicator, with a value of 1 indicating enable and a value of 0 indicating disable.

[0154] Optionally, in S303, after the first node sends the second information indicating that the first mapping relationship is not working properly, during the transition period before receiving further instructions (such as a second mapping relationship) from the second node, the first node may still need to report precoding information for downlink scheduling. During this transition period, the first node cannot continue to use the confirmed malfunctioning first mapping relationship to calculate precoding information; otherwise, it will result in reporting inaccurate channel state information.

[0155] To address the aforementioned issues, after transmitting the second information, the first node can determine the sixth information based on a predefined method. This sixth information is used for downlink channel precoding. Specifically, determining the sixth information based on a predefined method includes at least one of the following: Method 1: Determine the sixth information corresponding to the first channel measurement information based on the fourth mapping relationship. The fourth mapping relationship is a pre-configured mapping relationship by the second node, such as a pre-configured downloadable codebook or a pre-configured artificial intelligence model. The second node can indicate the identification information of the fourth mapping relationship to the first node via signaling (such as RRC signaling or MAC-CE). For example, the second node pre-configures two downloadable codebooks, codebook A and codebook B. When the first node uses codebook A and detects an abnormal operation, it can switch to codebook B to calculate the pre-coded information. Similarly, when the first node uses artificial intelligence model A and detects an abnormal operation, it can switch to the pre-configured artificial intelligence model B to calculate the latent vector.

[0156] Method 2: Determine the sixth information corresponding to the first channel measurement information based on the third mapping relationship. The third mapping relationship is built into the first node and always exists in the first node's storage, requiring no additional configuration. For example, in a downloadable codebook scenario, the third mapping relationship can be a fixed codebook built into the first node at the factory (such as a Type I codebook, a Type II codebook, or a newly defined codebook in 6GR). If the downloadable codebook is faulty, the first node can fall back to the built-in fixed codebook to calculate the PMI. In an AI model-based scenario, the third mapping relationship can be the default AI model built into the first node, such as a general model with low computational complexity and strong generalization ability.

[0157] Method 3: Update the first mapping relationship, and determine the sixth information corresponding to the first channel measurement information based on the updated first mapping relationship. Specifically, the first node can perform partial updates or parameter adjustments to the first mapping relationship. For example, when the first mapping relationship is a downloadable codebook, the first node can adjust some basis vectors in the codebook; when the first mapping relationship is an artificial intelligence model, the first node can incrementally update the model parameters. The updated first mapping relationship can better adapt to the current channel conditions, and the first node recalculates the sixth information based on the updated mapping relationship.

[0158] Optionally, in scenarios where the sixth information is determined based on the third mapping relationship, when the aforementioned predefined method does not exist, the first node falls back to the third mapping relationship, i.e., the mapping relationship built into the first node, and determines the sixth information corresponding to the first channel measurement information based on this built-in mapping relationship. For example, in a downloadable codebook scenario, the third mapping relationship can be a fixed codebook built into the first node at the factory (such as a Type I codebook or a Type II codebook, or a newly defined codebook in 6GR). When the downloadable codebook is abnormal and there is no pre-configured alternative codebook, the first node falls back to the built-in fixed codebook to calculate the PMI. In scenarios based on artificial intelligence models, the third mapping relationship can be a default artificial intelligence model built into the first node, such as a general model with low computational complexity and strong generalization ability. When the current artificial intelligence model is abnormal and there is no pre-configured alternative model, the first node falls back to the built-in default model to calculate the latent vector.

[0159] In some implementations, the first node sends a seventh message, which is used to indicate the identification information of the mapping relationship used by the first node to determine the sixth message.

[0160] For example, when the first node determines the sixth information based on the fourth mapping relationship, the seventh information indicates the identification information of the fourth mapping relationship. For example, the second node is pre-configured with codebook A and codebook B. When the first node uses codebook A and detects an abnormal operation, it switches to codebook B to calculate the pre-encoded information. At this time, the seventh information carries the identification information of codebook B. Upon receiving the seventh information, the second node can know that the first node has switched to codebook B and uses the decoding method corresponding to codebook B to reconstruct the channel state information.

[0161] When the first node determines the sixth information based on the third mapping relationship, the seventh information indicates the identification information of the third mapping relationship. For example, in a downloadable codebook scenario, the first node reverts to the factory-built Type I codebook to calculate the PMI. In this case, the seventh information carries the identification information of the Type I codebook. The second node then knows that the first node has reverted to the built-in codebook and adjusts its decoding method and scheduling strategy accordingly. The identifier carried in the seventh information can be the ID of the reverted default codebook or the ID of the new codebook, or a preset model ID after the switch. It can also be a bit 1 (revert) / 0 (not reverted), indicating whether the currently reported CSI is calculated using the reverted codebook.

[0162] When the first node determines the sixth information based on the updated first mapping relationship, the seventh information indicates the identification information of the updated first mapping relationship. For example, after the first node performs a local update on some basis vectors in the first codebook, the seventh information carries the version identification information of the updated codebook. The second node then knows that the codebook has been changed and processes it using the decoding method corresponding to the updated codebook.

[0163] Optionally, when the first node falls back to the built-in third mapping relationship to determine the sixth information, the seventh information carries the identification information of the built-in codebook. Upon receiving the seventh information, the second node can then know that the first node has fallen back to the default codebook. Similarly, in scenarios based on artificial intelligence models, when the current model is abnormal and there is no pre-configured alternative model, the first node falls back to the built-in default artificial intelligence model to calculate the latent vector. The seventh information carries the identification information of the default model, and the second node loads the corresponding decoder model accordingly to reconstruct the channel state information.

[0164] Optionally, the seventh information and the sixth information can be sent together in the same message, or sent independently before or after the sixth information. Optionally, the specific form of the seventh information may include at least one of the following: an index identifier of the mapping relationship, such as a codebook index, model index, or version number; an indication of the mapping relationship type, such as indicating whether the current method is codebook-based or artificial intelligence model-based, and the specific codebook type or model type.

[0165] S304, the second node determines whether to change the first mapping relationship based on the second information.

[0166] According to the three methods in S303, the behavior of the second node in determining whether to change the first mapping relationship based on the second information includes the following three methods: In Method 1, when the second information contains the judgment result of the first node, the second node directly decides whether to change the first mapping relationship based on that judgment result. Optionally, when the second information also contains a suggested new codebook identifier, codebook pairing identifier, or new model identifier, the second node can select the corresponding second mapping relationship based on that identifier.

[0167] Method 2: When the second information contains the calculation result, the second node compares the calculation result with the corresponding preset threshold. When the calculation result meets the preset judgment condition (such as greater than or equal to the threshold, less than or equal to the threshold, depending on the specific statistical type), it is determined that the first mapping relationship needs to be changed.

[0168] Method 3: When the second information includes the first information and the reference information, the second node can use the same calculation method as in Method 1 to calculate the statistic based on the first information and the reference information, and compare the statistic with the corresponding preset threshold to determine whether to change the first mapping relationship. The second node can also make a comprehensive judgment by combining other information from the network side.

[0169] If it is determined that the first mapping relationship needs to be changed, the second node sends the second mapping relationship to the first node. When the first mapping relationship is the first codebook, the second mapping relationship is the second codebook, and the first node uses the second codebook to replace the first codebook for subsequent PMI calculations and reporting. When the first mapping relationship is the first AI model, the second mapping relationship is the second AI model, and the first node uses the second AI model to replace the first AI model for subsequent latent vector generation and reporting. If it is determined that the first mapping relationship does not need to be changed, the first node continues to use the current mapping relationship.

[0170] Optionally, when the first mapping relationship is the first codebook, replacing the first codebook includes at least one of the following methods: updating the first codebook, that is, the second node sends a completely new codebook to the first node, and the first node uses the new codebook to replace the first codebook; falling back to a specified codebook, that is, the second node instructs the first node to fall back to a previously used codebook; updating some basis vectors in the first codebook, that is, the second node sends the basis vectors in the first codebook that need to be replaced to the first node, and the first node only updates some basis vectors, while the remaining basis vectors remain unchanged.

[0171] When the first mapping relationship is the first artificial intelligence model, replacing the first artificial intelligence model includes at least one of the following methods: the second node sends a brand new artificial intelligence model (including an encoder model and / or a decoder model) to the first node, and the first node uses the new model to replace the first artificial intelligence model; the second node sends model update parameters to the first node, and the first node performs incremental updates to the first artificial intelligence model based on the update parameters.

[0172] In this embodiment, the first node determines whether the first mapping relationship is still applicable based on the comparison result between the first information and the reference information. When the performance of the mapping relationship deteriorates, the first node reports the second information to the second node to trigger the mapping relationship replacement. By using the precoding information output by the mapping relationship and the reference information for difference quantization at the terminal side, the first node can pre-determine whether the mapping relationship is normal before the second node actually uses the current mapping relationship to schedule downlink data. This helps to realize the early detection and timely replacement of the mapping relationship when it is inapplicable, and avoids the system performance loss caused by the second node using inaccurate channel state information for scheduling. This scheme is applicable to both traditional codebooks and artificial intelligence-based precoding models. Through a unified mapping relationship evaluation framework, it realizes the universal applicability monitoring of different precoding schemes.

[0173] In the above embodiments, first information corresponding to the channel measurement information is determined based on the first mapping relationship, and reference information is obtained. Whether to change the first mapping relationship is then determined based on the first information and / or the reference information. In another optional embodiment, the decision to change the first mapping relationship can also be based on changes in channel attribute information associated with the first mapping relationship.

[0174] Figure 4 This is a flowchart illustrating another communication method according to an embodiment of this application. In this embodiment, it is determined whether to change the first mapping relationship based on changes in channel attribute information associated with the first mapping relationship.

[0175] S401, the first node obtains the reference value of the channel attribute information between the first node and the second node.

[0176] The first node acquires a channel attribute information reference value, which is used to compare with the first channel attribute information obtained from subsequent measurements to determine whether the channel environment has changed significantly. The channel attribute information reference value can reflect the baseline state of the channel environment when the first mapping relationship is first used. For example, when the first mapping relationship is a first codebook, the channel attribute information reference value can be a characteristic value of the channel environment when the first codebook is activated; when the first mapping relationship is a first artificial intelligence model, the channel attribute information reference value can be a characteristic value of the channel environment when the model is deployed.

[0177] The first node can obtain channel attribute information reference values ​​through at least one of the following methods: Method 1, pre-configuration by the second node. The second node sends the pre-configured reference value to the first node via RRC signaling or MAC CE. For example, the second node pre-configures a reference value of 0.8 for a time domain channel property (TDCP), and the first node compares the current TDCP value with this reference value in subsequent measurements. Method 2, self-measurement by the first node. When the first mapping relationship is first used (e.g., when the first codebook is activated or the first artificial intelligence model is deployed), the first node performs an initial measurement of the channel attribute information and uses this initial measurement value as the reference value. For example, the first node measures the current TDCP value at the moment the first codebook is activated as the reference value, and then continuously measures the TDCP and compares it with the initial value. When the difference between the two is significant, it indicates that the channel environment has changed. Method 3, determination by the first node based on historical measurement values. In the initial stage of using the first mapping relationship, the first node performs multiple measurements of the channel attribute information and takes statistical values ​​(such as the mean or median) as reference values ​​to reduce the impact of randomness in a single measurement.

[0178] S402, the first node obtains the first channel attribute information, and the first channel attribute information is associated with the first mapping relationship.

[0179] The first node acquires first channel attribute information. This first channel attribute information represents the long-term statistical characteristics of the channel, describing its variations across different dimensions. The first channel attribute information includes at least one of the following: time-domain channel attributes between the first and second nodes, reflecting changes in channel correlation over time, including variations in channel autocorrelation amplitude and phase; frequency-domain channel attributes between the first and second nodes, reflecting changes in channel correlation over frequency; and spatial-domain channel attributes between the first and second nodes, reflecting changes in channel correlation over space. The first channel attribute information is correlated with a first mapping relationship; that is, the first channel attribute information is measured during the use of the first mapping relationship, and its changes reflect whether significant long-term changes have occurred in the wireless environment during the period of using the first mapping relationship. When the first mapping relationship is a first codebook, the first channel attribute information reflects the long-term changes in the channel environment during the use of the codebook; when the first mapping relationship is a first artificial intelligence model, the first channel attribute information reflects the long-term changes in the channel environment during the use of the model. Correspondingly, the second node acquires the first channel attribute information associated by the first node based on the first mapping relationship.

[0180] S403, the first node sends the eighth information based on the first channel attribute information and the channel attribute information reference value. The eighth information is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0181] Correspondingly, the second node receives the eighth information sent by the first node based on the first channel attribute information and the channel attribute information reference value.

[0182] The first node compares the currently measured first channel attribute information with the channel attribute information reference value, and generates and sends the eighth message based on the comparison result. Depending on the content of the eighth message, the first node's behavior includes at least one of the following methods: Method 1: The first node automatically determines whether the first mapping relationship needs to be changed and sends the result as the eighth piece of information. Specifically, the first node calculates the difference between the first channel attribute information and the reference value of the channel attribute information, and compares the difference with a second condition (such as a preset second threshold). For example, for TDCP, if the difference between the TDCP value of the first channel attribute information and the reference value does not meet the second condition (such as the difference being greater than or equal to the second threshold), it indicates that the time-domain correlation characteristics of the channel have changed significantly, and the first node determines that the first mapping relationship is no longer applicable and needs to be changed. Optionally, the first node can count the number of times the difference does not meet the second condition within a preset time window. If the number of times it does not meet the condition exceeds the preset number, the first mapping relationship is determined to be no longer applicable. Alternatively, if the trend of TDCP changes exceeds a preset value within a preset measurement time, or if the number of times the trend of TDCP changes exceeds the preset value exceeds the preset number, the first mapping relationship is determined to be no longer applicable.

[0183] Optionally, before the first node determines whether the first mapping relationship needs to be changed, the first node continuously monitors channel attribute information during the use of the first mapping relationship. Channel attribute information includes at least one of time-domain channel attributes, frequency-domain channel attributes, and spatial-domain channel attributes. When the change in the characteristics of at least one dimension of the monitored channel attribute information exceeds a pre-configured threshold, the first node is triggered to calculate the difference between the first channel attribute information and the channel attribute information reference value, and determines whether the first mapping relationship needs to be changed based on this difference. For example, if the first node simultaneously monitors both TDCP and SDCP dimensions, when the change in TDCP exceeds a pre-configured threshold, or the change in SDCP exceeds a pre-configured threshold, or both exceed pre-configured thresholds, the first node can trigger the difference calculation and mapping relationship applicability judgment process. Optionally, each dimension can share the same pre-configured threshold, or different pre-configured thresholds can be configured separately.

[0184] In this method, the eighth information can carry at least one of the following indications: First, indicating whether the second node should change the first mapping relationship, for example, a 1-bit indication, where a value of 1 indicates that it needs to be changed and a value of 0 indicates that it does not need to be changed; Second, indicating whether the first mapping relationship is working normally, for example, a value of 1 indicates that it is not working normally and a value of 0 indicates that it is working normally; Third, indicating whether the first channel attribute information meets the preset conditions, for example, when the first channel attribute information does not meet the preset conditions (such as the TDCP value being lower than the preset minimum threshold or exceeding the preset maximum threshold), the first node reports to the second node through the eighth information that the channel attribute information has become abnormal, and the second node can determine whether it needs to trigger the mapping relationship to be changed based on the report.

[0185] In this approach, the first node completes the assessment and judgment of the applicability of the mapping relationship, and the second node directly decides whether to perform the replacement based on the judgment result of the first node. Optionally, when the eighth message indicates the replacement of the first mapping relationship or the first mapping relationship is not working properly, the first node can also carry a suggested new codebook identifier, codebook pairing identifier, or new model identifier in the eighth message, so as to simultaneously instruct the second node to send the second mapping relationship in the eighth message.

[0186] In method two, the first node sends the difference between the first channel attribute information and the reference value of the channel attribute information as the eighth piece of information to the second node. The second node then determines whether to change the first mapping relationship based on this difference. In this method, the first node calculates the difference but does not perform the applicability judgment; the judgment process is completed by the second node. After receiving the difference, the second node compares it with the second condition. If the difference does not meet the second condition, it determines that the first mapping relationship needs to be changed.

[0187] In method three, the first node sends the first channel attribute information and the channel attribute information reference value as the eighth piece of information to the second node. The second node then calculates the difference and determines whether to change the first mapping relationship. That is, the eighth piece of information includes at least one of the following: the first channel attribute information and the channel attribute information reference value. In this method, the first node does not perform an applicability judgment; it only reports the original channel attribute information and reference value. The judgment process is completed by the second node. After receiving the first channel attribute information and reference value, the second node calculates the difference and compares it with the second condition to determine whether to change the first mapping relationship. Furthermore, the second node can also combine other information from the network side (such as channel attribute information reports from other terminal devices, overall cell channel statistics, etc.) for a comprehensive judgment, providing greater decision-making flexibility.

[0188] S404, the second node determines whether to change the first mapping relationship based on the eighth information.

[0189] The second node receives the eighth message sent by the first node and determines whether the first mapping relationship needs to be changed based on the eighth message. According to the three methods in S403, the behavior of the second node includes the following three methods: In Method 1, when the eighth message contains the judgment result of the first node, the second node directly decides whether to replace the first mapping relationship based on that judgment result. Specifically, when the eighth message indicates that the first mapping relationship needs to be replaced or that the first mapping relationship is not working properly, the second node determines to replace the first mapping relationship. When the eighth message indicates that the first channel attribute information does not meet the preset conditions, the second node determines whether to trigger a mapping relationship replacement based on the report. For example, the second node can comprehensively analyze the report with the channel attribute information reports of other terminal devices on the network side to determine whether the current channel environment change is a regional change or a local change, thereby making a more accurate replacement decision. Optionally, when the eighth message also contains a suggested new codebook identifier, codebook pairing identifier, or new model identifier, the second node can select the corresponding second mapping relationship based on the identifier and send the second mapping relationship to the first node.

[0190] Method 2: When the eighth information contains the difference between the first channel attribute information and the channel attribute information reference value, the second node compares the difference with the second condition (such as the preset second threshold). When the difference does not meet the second condition, it is determined that the first mapping relationship needs to be changed.

[0191] Method 3: When the eighth information includes the first channel attribute information and a reference value for the channel attribute information, the second node calculates the difference between the first channel attribute information and the reference value, compares the difference with the second condition, and determines whether to change the first mapping relationship. The second node can also combine other information from the network side for comprehensive judgment, providing greater decision-making flexibility.

[0192] If the first mapping relationship is changed, the second node sends the second mapping relationship to the first node. When the first mapping relationship is the first codebook, the second mapping relationship is the second codebook, and the first node uses the second codebook to replace the first codebook for subsequent PMI calculation and reporting. When the first mapping relationship is the first artificial intelligence model, the second mapping relationship is the second artificial intelligence model, and the first node uses the second artificial intelligence model to replace the first artificial intelligence model for subsequent latent vector generation and reporting.

[0193] In some implementations, the second node can also send a ninth message to the first node. This ninth message instructs the first node to send an eighth message based on the first channel attribute information and a channel attribute information reference value. For example, the ninth message may include the following configuration parameters: a second condition (such as a second threshold), the type of channel attribute information being monitored (time domain / frequency domain / spatial domain), and a preset time window length.

[0194] In this embodiment, the first node assesses whether the first mapping relationship still matches the current channel conditions by monitoring the long-term statistical characteristics of the channel, and reports the assessment result or relevant channel attribute information to the second node through the eighth information. The second node determines whether to replace the first mapping relationship based on the eighth information. Compared with comparison methods based on instantaneous measurements, channel attribute information reflects the long-term trend of channel changes. These changes usually indicate a substantial change in the wireless environment, at which point the first mapping relationship truly needs to be replaced. Using a judgment method based on the long-term statistical characteristics of the channel helps reduce unnecessary mapping relationship switching caused by short-term channel fluctuations (such as instantaneous deep fading), and improves the stability and reliability of mapping relationship replacement judgments. This scheme is applicable to both traditional codebooks and AI-based precoding models. Through a unified mapping relationship evaluation framework, it achieves universal applicability monitoring of different precoding schemes based on long-term channel changes. Simultaneously, it helps the second node to promptly grasp changes in the long-term characteristics of the channel and make replacement decisions in advance when the mapping relationship is about to become inapplicable.

[0195] In some implementations, the communication methods provided in the embodiments of this application can be used in combination. In one example, the first node or the second node can be implemented simultaneously. Figure 3 The illustrated embodiments and Figure 4 The solution of the embodiment shown: when through Figure 3 When the method of the illustrated embodiment determines that the first mapping relationship is unsuitable, if the change in at least one channel attribute statistic exceeds a preset threshold simultaneously, then the mapping relationship is changed. In another example, the first node or the second node can be implemented independently. Figure 4 The method of the illustrated embodiment is used for mapping relationship monitoring. The above embodiments can be implemented independently or in combination according to actual needs; this application does not limit this.

[0196] The above text, in conjunction with Figures 1 to 12, shows... Figure 4 The method embodiments of this application are described in detail below, in conjunction with... Figures 5 to 8 The present application provides a detailed description of the apparatus embodiments. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be found in the foregoing method embodiments.

[0197] Figure 5 This is a schematic diagram of the structure of a terminal device provided in another embodiment of this application. Figure 5 The terminal device 500 shown can be the terminal described above. The terminal device 500 may include a first transceiver unit 510 and a first processing unit 520.

[0198] In one possible embodiment, the first transceiver unit 510 may be used to send second information, which is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0199] In one possible embodiment, the first transceiver unit 510 can also be used to send first information.

[0200] In one possible embodiment, the first transceiver unit 510 may also send eighth information based on the first channel attribute information and the channel attribute information reference value. The eighth information is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0201] In one possible embodiment, the first processing unit 520 can also be used to determine the first information corresponding to the first channel measurement information based on the first mapping relationship, and the first information is used for downlink channel precoding.

[0202] In one possible embodiment, the first processing unit 520 can also be used to obtain reference information corresponding to the first channel measurement information.

[0203] As one embodiment, the first transceiver unit 510 can be a transceiver 730, the first processing unit 520 can be a processor 710, and the terminal device 500 may further include a storage unit, which can be a memory 720, specifically as follows: Figure 7 As shown.

[0204] Figure 6 This is a schematic diagram of a network device provided in another embodiment of this application. The network device 600 may include a second transceiver unit 610 and a second processing unit 620.

[0205] In one possible embodiment, the second transceiver unit 610 can be used to receive second information, which is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0206] In one possible embodiment, the second transceiver unit 610 can also be used to receive the first information.

[0207] In one possible embodiment, the second transceiver unit 610 can also be used to send downlink signals based on the first information.

[0208] In one possible embodiment, the second transceiver unit 610 can also be used to receive eighth information, which is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

[0209] As one embodiment, the second transceiver unit 610 can be a transceiver 730, and the second processing unit 620 can be a processor 710. The network device 600 may also include a storage unit, which can be a memory 720, specifically as follows... Figure 7 As shown.

[0210] Figure 7 This is a schematic diagram of the structure of a communication device provided in another embodiment of this application. Figure 7 The dashed lines in the diagram indicate that the unit or module is optional. The device 700 can be used to implement the methods described in the above method embodiments. The device 700 can be a chip, user equipment, or network device.

[0211] The apparatus 700 may include one or more processors 710. The processor 710 may support the apparatus 700 in implementing the methods described in the preceding method embodiments. The processor 710 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0212] The apparatus 700 may also include one or more memories 720. The memories 720 store a program that can be executed by the processor 710, causing the processor 710 to perform the methods described in the preceding method embodiments. The memories 720 may be independent of the processor 710 or integrated within the processor 710.

[0213] The device 700 may also include a transceiver 730. The processor 710 can communicate with other devices or chips via the transceiver 730. For example, the processor 710 can send and receive data with other devices or chips via the transceiver 730.

[0214] Figure 8 This is a schematic diagram of the hardware module of the communication device provided in an embodiment of this application. Specifically, Figure 8 A block diagram of a first communication device 850 and a second communication device 810 communicating with each other in an access network is shown.

[0215] The first communication device 850 includes a controller / processor 859, a memory 860, a data source 867, a transmitting processor 868, a receiving processor 856, a multi-antenna transmitting processor 857, a multi-antenna receiving processor 858, a transmitter / receiver 854, and an antenna 852.

[0216] The second communication device 810 includes a controller / processor 875, a memory 876, a data source 877, a receiver processor 870, a transmitter processor 816, a multi-antenna receiver processor 872, a multi-antenna transmitter processor 871, a transmitter / receiver 818, and an antenna 820.

[0217] In the transmission from the second communication device 810 to the first communication device 850, at the second communication device 810, upper-layer data packets from the core network or from the data source 877 are provided to the controller / processor 875. The core network and data source 877 represent all protocol layers above the L2 layer. The controller / processor 875 implements the functionality of the L2 layer. In the transmission from the second communication device 810 to the first communication device 850, the controller / processor 875 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation for the first communication device 850 based on various priority metrics. The controller / processor 875 is also responsible for retransmitting lost packets and signaling to the first communication device 850. The transmit processor 816 and the multi-antenna transmit processor 871 implement various signal processing functions for the L1 layer (i.e., the physical layer). Transmit processor 816 performs encoding and interleaving to facilitate forward error correction at the second communication device 810, and mapping of signal clusters based on various modulation schemes (e.g., binary phase shift keying, quadrature phase shift keying, M-phase shift keying, M-quadrature amplitude modulation). Multi-antenna transmit processor 871 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based and non-codebook-based precoding, and beamforming processing, generating one or more spatial streams. Transmit processor 816 then maps each spatial stream to subcarriers, multiplexes it with a reference signal (e.g., a pilot) in the time and / or frequency domains, and then uses inverse fast Fourier transform to generate a physical channel carrying the time-domain multicarrier symbol stream. Multi-antenna transmit processor 871 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 818 converts the baseband multicarrier symbol stream provided by multi-antenna transmit processor 871 into an RF stream, which is then provided to different antennas 820.

[0218] In the transmission from the second communication device 810 to the first communication device 850, at the first communication device 850, each receiver 854 receives a signal through its corresponding antenna 852. Each receiver 854 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 856. The receiver processor 856 and the multi-antenna receiver processor 858 implement various signal processing functions of Layer 1. The multi-antenna receiver processor 858 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 854. The receiver processor 856 uses a fast Fourier transform to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 856, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 858 after multi-antenna detection to recover any spatial stream destined for the first communication device 850. Symbols on each spatial stream are demodulated and recovered in the receiver processor 856, generating soft decisions. The receiver processor 856 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted by the second communication device 810 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 859. The controller / processor 859 implements the functions of Layer 2. The controller / processor 859 may be associated with a memory 860 storing program code and data. The memory 860 may be referred to as computer-readable media. In the transmission from the second communication device 810 to the first communication device 850, the controller / processor 859 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover the upper-layer data packets from the second communication device 810. The upper-layer data packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 for Layer 3 processing.

[0219] In the transmission from the first communication device 850 to the second communication device 810, at the first communication device 850, upper-layer data packets are provided to the controller / processor 859 using a data source 867. The data source 867 represents all protocol layers above the L2 layer. Similar to the transmission functions at the second communication device 810 described in the transmission from the second communication device 810 to the first communication device 850, the controller / processor 859 implements header compression, encryption, packet segmentation and reordering, and multiplexing between the logical and transport channels, implementing L2 layer functions for the user plane and control plane. The controller / processor 859 is also responsible for retransmitting lost packets and signaling to the second communication device 810. Transmit processor 868 performs modulation mapping and channel coding processing, while multi-antenna transmit processor 857 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming processing. Subsequently, transmit processor 868 modulates the generated spatial stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 857, the stream is provided to different antennas 852 via transmitter 854. Each transmitter 854 first converts the baseband symbol stream provided by multi-antenna transmit processor 857 into a radio frequency symbol stream before providing it to antenna 852.

[0220] In the transmission from the first communication device 850 to the second communication device 810, the function at the second communication device 810 is similar to the receiving function at the first communication device 850 described in the transmission from the second communication device 810 to the first communication device 850. Each receiver 818 receives radio frequency signals through its corresponding antenna 820, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 872 and the receiving processor 870. The receiving processor 870 and the multi-antenna receiving processor 872 jointly implement the L1 layer functions. The controller / processor 875 implements the L2 layer functions. The controller / processor 875 may be associated with a memory 876 that stores program code and data. The memory 876 may be referred to as computer-readable media. In the transmission from the first communication device 850 to the second communication device 810, the controller / processor 875 provides multiplexing between the transmission and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover upper-layer data packets from the first communication device 850. Upper-layer data packets from the controller / processor 875 can be provided to the core network or all protocol layers above the L2 layer, and various control signals can also be provided to the core network or L3 for L3 processing.

[0221] As an example, the first communication device 850 corresponds to the terminal in this application.

[0222] As an example, the second communication device 810 corresponds to the network device in this application.

[0223] As an example, the first communication device 850 is an NCR.

[0224] As an example, the first communication device 850 is a wireless repeater.

[0225] As one embodiment, the first communication device 850 is a relay.

[0226] As one embodiment, the first communication device 850 is a user equipment that can act as a relay node.

[0227] As an example, the first communication device 850 is a V2X-enabled user equipment that can act as a relay node.

[0228] As one embodiment, the first communication device 850 is a D2D-enabled user equipment that can act as a relay node.

[0229] As one embodiment, the second communication device 810 is a base station.

[0230] As one embodiment, the antenna 852, the receiver 854, the multi-antenna receiving processor 858, the receiving processor 856, and the controller / processor 859 are used to receive the first information in this application, etc.

[0231] As one embodiment, the antenna 820, the transmitter 818, the multi-antenna transmitter processor 871, the transmitter processor 816, and the controller / processor 875 are used to transmit the request signaling in this application.

[0232] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0233] This application also provides a chip including a memory and a processor, which can call and run computer programs from the memory to execute the methods performed by a terminal or network device in various embodiments of this application.

[0234] This application also provides a chip module, including a memory and a processor, which can call and run computer programs from the memory to execute the methods performed by a terminal or network device in various embodiments of this application.

[0235] This application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0236] This application also provides a computer program. This computer program can be applied to the terminal or network device provided in this application, and the computer program causes the computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0237] It should be understood that the terms "system" and "network" in this application can be used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the application. The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0238] In the embodiments of this application, the term "instruction" can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0239] In the embodiments of this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0240] In the embodiments of this application, the term "correspondence" can indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship such as instruction and being instructed, configuration and being configured.

[0241] In this application embodiment, "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including user equipment and network devices). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0242] In this application embodiment, the "protocol" may refer to a standard protocol in the field of communication, such as the LTE protocol, the NR protocol, and related protocols applied to future communication systems. This application does not limit this.

[0243] In the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0244] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0245] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0246] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0247] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0248] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0249] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for a first node in wireless communication, characterized in that, include: Based on the first mapping relationship, the first information corresponding to the first channel measurement information is determined, and the first information is used for downlink channel precoding. Obtain reference information corresponding to the second channel measurement information, wherein the second channel measurement information and the first channel measurement information are channel measurement information of the same channel; Based on the first information and / or the reference information, second information is sent, which is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

2. The method according to claim 1, characterized in that, The first information is first precoding information, and the reference information is reference precoding information; the second information includes at least one of the following: The difference between the signal power using the first precoding information and the signal power using the reference precoding information, the signal power of the difference between the first precoding information and the reference precoding information, the ratio of the signal power using the first precoding information to the signal power using the reference precoding information, the difference between the signal-to-noise ratio using the first precoding information and the signal-to-noise ratio using the reference precoding information, and the generalized cosine square similarity between the first precoding information and the reference precoding information.

3. The method according to claim 1, characterized in that, The second information indicates whether the second node should change the first mapping relationship.

4. The method according to claim 3, characterized in that, The second information instructs the second node to change the first mapping relationship, and the second information is also used to instruct the second node to send a second mapping relationship.

5. The method according to claim 1, characterized in that, The second information includes at least one of the following: the first information, the reference information, the channel estimation matrix determined based on the second channel measurement information, the precoding vector determined based on the second channel measurement information, the channel autocorrelation matrix determined based on the second channel measurement information, and the true value of the first channel measurement information.

6. The method according to any one of claims 1 to 5, characterized in that, The reference information is reference precoding information, the first mapping relationship is a first codebook, the second channel measurement information is the first channel measurement information, and obtaining the reference information corresponding to the second channel measurement information includes: The reference precoding information determined based on all or part of the basis vectors of the first codebook; or, The reference precoding information determined based on the first channel measurement information.

7. The method according to any one of claims 1 to 6, characterized in that, The first mapping relationship is a first artificial intelligence model, the first information is a latent vector, and the reference information is the true value of the first channel measurement information.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Receive third information, which is used to instruct the first node to send second information based on the first information and / or the reference information.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: Receive fourth information, which enables or disables the first node from sending the second information based on the first information and the reference information.

10. The method according to claim 1, characterized in that, The reference information is channel attribute information, which includes at least one of the following: time-domain channel attribute between the first node and the network device, frequency-domain channel attribute between the first node and the network device, or spatial-domain channel attribute between the first node and the network device. The channel attribute information is calculated based on the second channel measurement information. The step of sending the second information based on the reference information includes: sending the second information when the channel attribute information does not meet the first condition; or, If the number of times the channel attribute information fails to meet the first condition exceeds a preset number within a preset time period, the second information is sent.

11. The method according to claim 10, characterized in that, The method further includes: The fifth information is received, which is used to enable or disable the first node to determine whether the channel attribute information meets the first condition.

12. The method according to any one of claims 1 to 11, characterized in that, After sending the second information, the method further includes: The sixth information is determined based on a predefined method, and this sixth information is used for downlink channel precoding; or, The sixth information corresponding to the first channel measurement information is determined based on the third mapping relationship, wherein the third mapping relationship is a built-in mapping relationship of the first node, and the sixth information is used for downlink channel precoding; Send the sixth message.

13. The method according to claim 12, characterized in that, The determination of the sixth information based on a predefined method includes at least one of the following methods: The sixth information corresponding to the first channel measurement information is determined based on the fourth mapping relationship, wherein the fourth mapping relationship is a pre-configured mapping relationship; The sixth information corresponding to the first channel measurement information is determined based on the third mapping relationship, wherein the third mapping relationship is the mapping relationship built into the first node; Update the first mapping relationship, and determine the sixth information corresponding to the first channel measurement information based on the updated first mapping relationship.

14. The method according to claim 12 or 13, characterized in that, The method further includes sending a seventh message, the seventh message being used to instruct the first node to identify the mapping relationship used by the sixth message.

15. A method for a second node in wireless communication, characterized in that, include: The second information is received, which is sent based on reference information corresponding to the first information and the second channel measurement information. The first information is used for downlink channel precoding. The first information is determined by the first node based on the first channel measurement information and the first mapping relationship. The second channel measurement information and the first channel measurement information are channel measurement information of the same channel. Based on the second information, determine whether to change the first mapping relationship or whether the first mapping relationship is working properly.

16. The method according to claim 15, characterized in that, The first information is first precoding information, the reference information is reference precoding information, and the second information includes at least one of the following: The difference between the signal power using the first precoding information and the signal power using the reference precoding information, the signal power of the difference between the first precoding information and the reference precoding information, the ratio of the signal power using the first precoding information to the signal power using the reference precoding information, the difference between the signal-to-noise ratio using the first precoding information and the signal-to-noise ratio using the reference precoding information, and the generalized cosine square similarity between the first precoding information and the reference precoding information.

17. The method according to claim 15, characterized in that, The second information indicates whether the first mapping relationship should be changed.

18. The method according to claim 15, characterized in that, The second information includes at least one of the following: the first information, the reference information, the channel estimation matrix determined based on the second channel measurement information, the precoding vector determined based on the second channel measurement information, the channel autocorrelation matrix determined based on the second channel measurement information, and the true value of the first channel measurement information.

19. The method according to claim 18, characterized in that, The step of determining whether to change the first mapping relationship based on the second information includes: Whether to change the first mapping relationship is determined based on at least one of the following: the first information, the reference information, the channel estimation matrix determined based on the second channel measurement information, the precoding vector determined based on the second channel measurement information, the channel autocorrelation matrix determined based on the second channel measurement information, and the true value of the first channel measurement information.

20. The method according to any one of claims 15 to 19, characterized in that, The method further includes: Send a third message to the first node, the third message being used to instruct the first node to send the second message based on the first message and the reference information.

21. The method according to any one of claims 15 to 20, characterized in that, The method further includes: Send a fourth message, which enables or disables the first node from sending the second message based on the first message and the reference information.

22. The method according to claim 15, characterized in that, The reference information is channel attribute information, which includes at least one of the following: time-domain channel attribute between the first node and the second node, frequency-domain channel attribute between the first node and the second node, or spatial-domain channel attribute between the first node and the second node. The channel attribute information is calculated based on the second channel measurement information.

23. The method according to claim 22, characterized in that, The method further includes: Send a fifth message, which is used to enable or disable the first node to determine whether the channel attribute information meets the first condition.

24. A method for a first node in wireless communication, characterized in that, include: Obtain reference values ​​for channel attribute information between the first node and the second node; Obtain first channel attribute information, which is associated with a first mapping relationship; Based on the first channel attribute information and the channel attribute information reference value, an eighth message is sent, which is used to determine whether to change the first mapping relationship or to determine whether the first mapping relationship is working properly.

25. The method according to claim 24, characterized in that, The eighth piece of information includes the difference between the first channel attribute information and the reference value of the channel attribute information.

26. The method according to claim 24, characterized in that, The eighth information includes at least one of the following: the first channel attribute information, and the channel attribute information reference value.

27. The method according to claim 24, characterized in that, The eighth information indicates whether the second node has changed the first mapping relationship or whether the first mapping relationship is working properly, or whether the first channel attribute information does not meet the preset conditions.

28. The method according to claim 27, characterized in that, When the eighth information indicates that the first mapping relationship needs to be changed or that the first mapping relationship is not working properly, the eighth information is also used to instruct the second node to send a second mapping relationship.

29. The method according to claim 27 or 28, characterized in that, When the eighth information indicates whether the second node has changed the first mapping relationship or whether the first mapping relationship is working properly, the method includes: When the difference between the first channel attribute information and the channel attribute information reference value does not satisfy the second condition, the eighth information is sent; or, If the difference between the first channel attribute information and the reference value of the channel attribute information fails to meet the second condition more than a preset number of times within a preset time period, the eighth information is sent.

30. The method according to any one of claims 24 to 29, characterized in that, The channel attribute information includes at least one of the following: The time-domain channel attribute between the first node and the second node, the frequency-domain channel attribute between the first node and the second node, or the spatial-domain channel attribute between the first node and the second node.

31. The method according to any one of claims 24 to 30, characterized in that, The method further includes: The ninth message is received, which instructs the first node to send the eighth message based on the first channel attribute information and the channel attribute information reference value.

32. A method for a second node in wireless communication, characterized in that, include: Receive the eighth information, which is sent based on the first channel attribute information and the channel attribute information reference value, wherein the first channel attribute information is associated with the first mapping relationship; Based on the eighth piece of information, determine whether to change the first mapping relationship or whether the first mapping relationship is working properly.

33. The method according to claim 32, characterized in that, The eighth piece of information includes the difference between the first channel attribute information and the reference value of the channel attribute information.

34. The method according to claim 32, characterized in that, The eighth information includes at least one of the following: the first channel attribute information, and the channel attribute information reference value.

35. The method according to claim 32, characterized in that, The eighth piece of information indicates whether the first mapping relationship should be changed or whether the first mapping relationship is working properly.

36. The method according to claim 35, characterized in that, When the eighth information indicates that the first mapping relationship needs to be changed or that the first mapping relationship is not working properly, the eighth information is also used to instruct the second node to send a second mapping relationship.

37. The method according to any one of claims 32 to 36, characterized in that, When determining to change the first mapping relationship, the method further includes: Send the second mapping relationship.

38. The method according to any one of claims 32 to 37, characterized in that, The channel attribute information includes at least one of the following: The time-domain channel attribute between the first node and the second node, the frequency-domain channel attribute between the first node and the second node, or the spatial-domain channel attribute between the first node and the second node.

39. The method according to any one of claims 32 to 38, characterized in that, The method further includes: Send a ninth message to the first node, the ninth message being used to instruct the first node to send the eighth message based on the first channel attribute information and the channel attribute information reference value.

40. A communication device, characterized in that, Includes units or modules for performing the method as described in any one of claims 1-14, 15-23, 24-31 or 32-39.

41. A first node used for wireless communication, characterized in that, It includes a transceiver, a memory, and a processor, wherein the memory is used to store a program, the processor is used to invoke the program in the memory, and to control the transceiver to receive or send signals so that the node performs the method as described in any one of claims 1-14 or 24-31.

42. A second node used for wireless communication, characterized in that, The device includes a transceiver, a memory, and a processor. The memory is used to store a program, and the processor is used to invoke the program in the memory and control the transceiver to receive or send signals so that the node performs the method as described in any one of claims 15-23 or 32-39.

43. A communication device, characterized in that, The device includes at least one processor; and one or more non-transitory computer-readable storage media coupled to the at least one processor and storing programming instructions executable by the at least one processor, wherein the programming instructions, when executed, cause the at least one processor to perform the method as described in any one of claims 1-14, 15-23, 24-31 or 32-39.

44. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1-14, 15-23, 24-31, or 32-39.

45. A chip module, characterized in that, It includes a transceiver component and a chip, the chip being used to perform the method as described in any one of claims 1-14 or 24-31, or to perform the method as described in any one of claims 15-23 or 32-39.

46. ​​A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1-14, 15-23, 24-31 or 32-39.

47. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1-14, 15-23, 24-31 or 32-39.

48. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-14, 15-23, 24-31 or 32-39.

Images